parsers.py 文件源码

def pdf_parser(s):
    s = s.strip()
    # required to suppress warning messages
    with open(os.devnull, 'w') as fp:
        pdf = PdfFileReader(StringIO(s), strict=False, warndest=fp)
    if pdf.isEncrypted:
        try:
            pdf.decrypt('')
        except NotImplementedError:
            return {}
    meta = pdf.getDocumentInfo()
    #print(str(meta))
    result = {}
    for key in meta.keys():
        result[key[1:]] = meta.get(key)
    return result